StarMirror/data-science-ipython-notebooks
1
0
Fork 0
mirror of https://github.com/donnemartin/data-science-ipython-notebooks.git synced 2024-03-22 13:30:56 +08:00
Code Issues Projects Releases Wiki Activity

Added Random Forest: Prepare for Kaggle Submission section.

Browse Source
This commit is contained in:
Donne Martin 2015-03-20 11:36:41 -04:00
parent 055cd52cd3
commit 01d65fd232
1 changed files with 131 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

132
kaggle/titanic.ipynb
View File

@ -1,7 +1,7 @@
{
"metadata": {
"name": "",
"signature": "sha256:d50d4742eadf392ff4590f3569ff98f508db3dacbf33e0a31bd799b6bf4826ac"
"signature": "sha256:fa67591f8fc6a26469c4ee41e525877faea06787800b22b7273babe8116a05c4"
},
"nbformat": 3,
"nbformat_minor": 0,
@ -29,6 +29,7 @@
"* Data Munging Summary\n",
"* Random Forest: Training\n",
"* Random Forest: Predicting\n",
"* Random Forest: Prepare for Kaggle Submission\n",
"* Support Vector Machine: Training\n",
"* Support Vector Machine: Predicting"
]
@ -2552,6 +2553,135 @@
"metadata": {},
"outputs": [],
"prompt_number": 42
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Random Forest: Prepare for Kaggle Submission"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Create a DataFrame by combining the index from the test data with the output of predictions:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"result = np.c_[test_data[:, 0].astype(int), output.astype(int)]\n",
"df_result = pd.DataFrame(result[:, 0:2], columns=['PassengerId', 'Survived'])\n",
"df_result.head(10)"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>PassengerId</th>\n",
" <th>Survived</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td> 892</td>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> 893</td>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> 894</td>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> 895</td>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> 896</td>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td> 897</td>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td> 898</td>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td> 899</td>\n",
" <td> 0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td> 900</td>\n",
" <td> 1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td> 901</td>\n",
" <td> 0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 43,
"text": [
" PassengerId Survived\n",
"0 892 0\n",
"1 893 0\n",
"2 894 0\n",
"3 895 0\n",
"4 896 0\n",
"5 897 0\n",
"6 898 0\n",
"7 899 0\n",
"8 900 1\n",
"9 901 0"
]
}
],
"prompt_number": 43
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Write the results to csv:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"df_result.to_csv('../data/titanic/results-rf.csv', index=False)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 44
}
],
"metadata": {}